Model Releases

Liquid AI releases LFM2.5-Encoder-230M and 350M bidirectional encoders, fastest CPU inference at long context

Original title:LFM2.5-Encoders: Fast at Long Context, Even on CPU

AI summary

Liquid AI releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, two bidirectional encoders based on the LFM2 hybrid architecture that support an 8,192-token context and are available for download on Hugging Face.

Key Takeaways

  • Liquid AI releases LFM2.
  • 5-Encoder-230M and LFM2.
  • 5-Encoder-350M,two bidirectional encoders based on the LFM2 hybrid architecture that support an…

Quick Facts

Published
Updated
Source
Liquid AI 模型与工程博客(网页)
Category
Model Releases
AI score
65
Read the original Read the full article at the original source
Why it matters

原文给出双向编码器的架构改动、17 项任务微调评测和长上下文 CPU 吞吐对比,读者可以据此评估其在边缘和本地部署中的适用性。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Liquid AI releases LFM2.5-Encoder-230M and 350M bidirectional encoders, fastest CPU inference at long context. July 28, 2026. https://new.nat6.net/en/news/cmtym3yoy0006ronz5pdd728v/

View all →